Share this content on Facebook!
22 Sep 2016


AI With The Best will be the biggest online conference for data scientist, developers, tech teams and startups happening the 24th & 25th September 2016 bringing you 100 incredible speakers by having a novel, online conference platform. Meet Aerin Kim, Data Scientist turned Founding father of startup BYOR (Build Your Own Resume) speaking at AI Using the Best, online tech conference about her Phrase2Vec technology. Aerin is building an AI-based resume helper using NLP parsing. Every time a user uploads her resume for the webapp, it provides suggestions on the way to enhance your resume regarding its wording or phrases.

Please show somewhat about your background prior to BYOR and just how would you enter into data?

I used to be a NLP data scientist in a startup called Boxfish. I did so plenty of Twitter text modeling there and had been fascinated each day through the level of information that might be gleaned from all of the written text that men and women were generating. As it would have been a startup, all of us was building the merchandise on your own over many iterations. That training solved the problem later once i turned my idea in a product (BYOR).

What propelled that you push NLP parsing technology for Resum�s?

My co-founder and i also have already been volunteering as resume reviewers and mentors for Columbia University since 2014. Each year, we found there exists a pattern for weak resumes so we found ourselves giving students precisely the same advice year after year. We saw a way for some automation on this resume reviewing process.

Also at college career centers, it�s difficult to get a one-on-one session with career advisors as the student-to-advisor ratio is hundreds to one. We thought we would develop a tool that could be used by students to review their resume ahead of meeting their career advisors, or instead.

The BYOR project started since the class project for the CS 224d (Dr. Richard Socher) at Stanford. Rohit and that i took that class online.

How would you train the word embedding neural networks to discover similarities and relations between phrases?

The main way to find similarities and relations between two different phrases is converting these phones phrase vectors then seeking the distance between these vectors. There are many different methods to calculate phrase vectors. The most effective way that you can try is to first train the saying vectors then weight average those word vectors employed in the phrases.

So what can BYOR do in comparison to other CV checkers?

Currently, there is absolutely no company that suggests result phrases on a specific sentence. Even AI companies with good volume of funding don�t open their platforms like us. Inviting visitors to upload just about any resume and present them suggestions is a challenging problem on many levels and taking it on requires a little bravery.

What traditional CV checkers do is straightforward keyword extraction or keyword counting to check whether certain test is used or not. They don�t view the user�s resume line by line semantically.

What�s been the most exciting part of your startup adventure?

Probably the most exciting part happens when we help the �phrase suggestion algorithm� day-to-day and succeed in generating phrases that produce sense.

Also, prior to the startup, That i used to work with a big bank. If you are a employee of a giant company, your job description is quite narrowly focused. But in a startup, I can research every aspect in the product. It's been extreme fun for me thus far.

Also, it�s amazing to find out lots of people leading to BYOR voluntarily.

If it�s a well known fact, that is your favourite technological setup?

It�s a well known fact. We use python django for web. All NLP/deep learning code is presented in python.

To practice word vectors, we use code coded in C.

What advice would you give budding AI developers?

If you're AI developer, Applied Math basics are necessary to suit your needs. Invest several of your time and energy to talk about Linear Algebra, Optimization, Probability that you just learned during college.

Are you pumped up about speaking at AI Using the Best?

Yes! I like that it�s priced under 100 bucks so that average man or woman can attend. And it�s on the net!!! People/students shouldn�t must have sponsors to visit such tech conferences. With all the Best line-up is really as good being a $3000 conference.


There isn't any comment in this page yet!

Do you want to be the first commenter?

New Comment

Full Name:
E-Mail Address:
Your website (if exists):
Your Comment:
Security code: